"When you feel how depressingly slowly you climb, it's well to remember that Things Take Time" -Piet Hein

"When you get the chance to sit it out or dance, I hope you dance"

-Mark D. Sanders & Tia Sillers

Email: srijita1 [at] ualberta [dot] ca

Office address: Department of Computing Science

University of Alberta, 8900 114 St NW,

Edmonton, AB T6G 2S4

CV

Hello there!!

As of January, I have moved to University of Alberta as a Postdoctoral Fellow. I am part of the Intelligent Robot Learning Lab (IRL lab) and working with Professor Matthew Taylor . I completed my PhD in Computer Science from The University of Texas at Dallas under the supervision of Prof. Sriraam Natarajan . I was part of the StaRLing lab @ UTD .

My research interest spans across building sample-efficient models like Active Learning & Cost-sensitive learning to various decision making tasks like Reinforcement Learning, Inverse RL, Imitation learning etc in structured domains. I am also interested in leveraging human guidance to guide the sample-efficient and decision making models. Currently, I am interested in using human advice of different modalities and teacher-student framework to guide Reinforcement learning agents towards optimal behaviour more efficiently.

News:

  • My dissertation can be found here.

  • Our paper on Cost Aware Feature Elicitation received the honorable mention for best paper in CODS-COMAD 2021. Congrats to my awesome co-authors.

  • Paper on test-time feature elicitation accepted to CODS-COMAD 2021

  • My story got featured here

  • I have successfully defended my dissertation on Aug 31. Thanks to my wonderful committee members

  • Paper on Cost aware learning accepted to KIML 2020 workshop co-located with KDD

  • Paper on Fitted -Q for Relational RL accepted as poster paper in KR 2020.

  • Passed the PhD Candidacy exam

  • Presented my poster on "Active Feature Elicitation" in WiML 2019, Vancouver, Canada

Services:

  • Volunteer at WiML 2019, Vancouver, Canada

  • Reviewer at SDM 2020; CODS-COMAD 2020; AAAI 2021; AISTATS 2021, Frontiers in Big Data